% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@ARTICLE{Chen:271138,
      author       = {Chen, Dingfan and Oestreich, Marie and Afonja, Tejumade and
                      Kerkouche, Raouf and Becker, Matthias and Fritz, Mario},
      title        = {{T}owards {B}iologically {P}lausible and {P}rivate {G}ene
                      {E}xpression {D}ata {G}eneration},
      journal      = {Proceedings on privacy enhancing technologies},
      volume       = {2024},
      number       = {2},
      issn         = {2299-0984},
      address      = {Warsaw, Poland},
      publisher    = {De Gruyter Open},
      reportid     = {DZNE-2024-01006},
      pages        = {531 - 554},
      year         = {2024},
      abstract     = {Generative models trained with Differential Privacy (DP)
                      are becoming increasingly prominent in the creation of
                      synthetic data for downstream applications. Existing
                      literature, however, primarily focuses on basic benchmarking
                      datasets and tends to report promising results only for
                      elementary metrics and relatively simple data distributions.
                      In this paper, we initiate a systematic analysis of how DP
                      generative models perform in their natural application
                      scenarios, specifically focusing on real-world gene
                      expression data. We conduct a comprehensive analysis of five
                      representative DP generation methods, examining them from
                      various angles, such as downstream utility, statistical
                      properties, and biological plausibility. Our extensive
                      evaluation illuminates the unique characteristics of each DP
                      generation method, offering critical insights into the
                      strengths and weaknesses of each approach, and uncovering
                      intriguing possibilities for future developments. Perhaps
                      surprisingly, our analysis reveals that most methods are
                      capable of achieving seemingly reasonable downstream
                      utility, according to the standard evaluation metrics
                      considered in existing literature. Nevertheless, we find
                      that none of the DP methods are able to accurately capture
                      the biological characteristics of the real dataset. This
                      observation suggests a potential over-optimistic assessment
                      of current methodologies in this field and underscores a
                      pressing need for future enhancements in model design.},
      cin          = {AG Schultze / AG Becker},
      ddc          = {004},
      cid          = {I:(DE-2719)1013038 / I:(DE-2719)5000079},
      pnm          = {354 - Disease Prevention and Healthy Aging (POF4-354)},
      pid          = {G:(DE-HGF)POF4-354},
      typ          = {PUB:(DE-HGF)16},
      doi          = {10.56553/popets-2024-0062},
      url          = {https://pub.dzne.de/record/271138},
}